Fibroblast growth factor-21 enhances mitochondrial functions and increases the activity of PGC-1α in human dopaminergic neurons via Sirtuin-1

Abstract

Mitochondrial dysfunctions accompany several neurodegenerative disorders and contribute to disease pathogenesis among others in Parkinson's disease (PD). Peroxisome proliferator-activated receptor γ coactivator-1α (PGC-1α) is a major regulator of mitochondrial functions and biogenesis, and was suggested as a therapeutic target in PD. PGC-1α is regulated by both transcriptional and posttranslational events involving also the action of growth factors. Fibroblast growth factor-21 (FGF21) is a regulator of glucose and fatty acid metabolism in the body but little is known about its action in the brain. We show here that FGF21 increased the levels and activity of PGC-1α and elevated mitochondrial antioxidants in human dopaminergic cells in culture. The activation of PGC-1α by FGF21 occurred via the NAD(+)-dependent deacetylase Sirtuin-1 (SIRT1) subsequent to an increase in the enzyme, nicotinamide phosphoribosyltransferase (Nampt). FGF21 also enhanced mitochondrial respiratory capacity in human dopaminergic neurons as shown in real-time analyses of living cells. FGF21 is present in the brain including midbrain and is expressed by glial cells in culture. These results show that FGF21 activates PGC-1α and increases mitochondrial efficacy in human dopaminergic neurons suggesting that FGF21 could potentially play a role in dopaminergic neuron viability and in PD.

Keywords: Dopaminergic neurons; FGF21; Mitochondria; PGC-1α; Parkinson’s disease; SIRT1.

Figure 1

Effect of FGF21 on the expression and activation of PGC-1α in human dopaminergic neuron. Human dopaminergic neurons differentiated from midbrain progenitor cells were cultivated as described in Materials and methods. Cells were treated with 50 ng/ml FGF21 for 24 h as indicated below. (A) Left, immunoblot showing expression of tyrosine hydroxylase (TH) and dopamine transporter (DAT) in the human dopaminergic cells. β-actin was used as control. Right, phase contrast pictures. There was no significant difference in morphology between control and FGF21 treated cells. Scale bar. (B) Left, immunoblot. β-actin was used as control. The levels of PGC-1α were increased by FGF21. Right, quantification was done using ImageJ software. Values are means ± SD, n = 4, ***p < 0.001 for FGF21 vs C. (C) Gene promoter assays. Cells were transfected with the pGL3 basic plasmid and the PGC-1α promoter plasmids linked to a luciferase reporter. Cells were stimulated with FGF21 for 24 h and the luciferase activity was measured and corrected for that of Renilla as described as described in Methods. FGF21 enhanced PGC-1α gene activity but not that of the control pGL3 promoter. Values are means ± SD, n = 4, *p < 0.05 for FGF21 vs controls. (D) Immunoprecipitation experiments. PGC-1α was immunoprecipitated from control and FGF21-treated cells followed by immunoblotting as described in Methods. The degree of acetylation of PGC-1α was analyzed using the anti-acetylated lysine antibody. Total amount of PGC-1α in the immunoprecipitate was analyzed using anti- PGC-1α antibodies. Values are means ± SD, n = 4, *p < 0.05 for FGF21 vs C.

Figure 2

FGF21 increases SIRT1 and Nampt and the level of NAD ⁺ in human dopaminergic neurons. Human dopaminergic neurons were treated with 50 ng/ml FGF21 for 24 h as indicated below. (A-B) Immunoblots. β-actin was used as a control. The levels of SIRT1 (A) and Nampt (B) were increased by FGF21. Left, immunoblots. Right, quantifications using ImageJ. Values are means ± SD, n = 4, ***p < 0.001 and *p < 0.05 for FGF21-treated vs C. (C) The ratio of NAD⁺ to NADH in the dopaminergic neurons was measured as described in Methods. FGF21 increased NAD⁺ levels in the neurons. Values are means ± SD, n = 4, *p < 0.05 for FGF21 vs C. (D) Immunoprecipitation experiments. Cells were stimulated with FGF21 for 24 h in the absence or presence of 20 μM NAM to inhibit SIRT1. The degree of acetylation of PGC-1α was analyzed as above. Left, immunoblot. Right, quantification. FGF21 decreased PGC-1α acetylation in control cells but not in NAM treated cells. There was also an increase in acetylated PGC-1α due to SIRT1 inhibition as compared with controls. Values are means ± SD, n = 4, *p < 0.05 for FGF21 vs C.

Figure 3

FGF21 elevates mitochondrial antioxidants in the dopaminergic neurons. Human dopaminergic neurons were treated with 50 ng/ml FGF21 for 24 h followed by immunoblotting. (A) Immunoblots. β-actin was used as a control. FGF21 increased the levels Sod2 and Trx2 that are antioxidants localized to mitochondria. (B-C) Quantification. Sod2 (B) and Trx2 (C) increased in FGF21-treated neurons. Values are means ± SD, n = 4, **p < 0.01 or *p < 0.05 for FGF21 vs C.

Figure 4

Effect of FGF21 on the mitochondria respiratory capacity and mitochondria number in human dopaminergic neurons. Human dopaminergic neurons were stimulated with 50 ng/ml FGF21 and analyzed further as indicated below. (A) Oxygen consumption rate (OCR) in human dopaminergic neurons was measured in real-time using the Seahorse equipment as described in Methods. Typical graphs after addition of the various inhibitors are shown. (B) Quantification. Basal and maximum respiration (OCR) were increase in cells treated with FGF21 as was the spare respiratory capacity. Values are means ± SD, n = 4. ***p < 0.001 for FGF21 vs C. (C) Immunoblots. β-actin was used as control. The mitochondrial proteins TFAM and COX IV showed no significant changed in dopaminergic neurons treated with FGF21. (D) The mitochondrial DNA (mtDNA) copy number was analyzed using quantitative PCR as described in Methods. There was no change in the relative ratio of mtDNA to nuclear DNA reflecting an equal number of mitochondria in control and FGF21-treated dopaminergic cells. (E-F) Mitochondrial surface area. Left, control and FGF21 treated cells were analyzed by electron microscopy and the relative mitochondrial area was calculated from EM pictures as described in Methods. There were no significant changes in the mitochondrial surface area between control and FGF21 treated cells. Values are means means ± SD, n = 4. Right, typical EM pictures of control and FGF treated cells.

Figure 5

FGF21 is expressed in brain tissue and by glia cells in culture. (A) Brain regions from adult mice were dissected and subjected to immunoblotting using anti-FGF21 antibodies. β-actin was used as control. FGG21 is present in all brain areas. Two bands are detected representing the precursor and processed, mature form of FGF21 respectively. SN, substantia nigra; ST, striatum; HC, Hippocampus; CX, Cortex. (B) Immunoblot. Glia cell cultures were made from neonatal rat brain as described in Methods. Immunoblotting of cell lysates were performed using anti-FGF21 antibodies. The human hepatocyte cell line (Huh7) was used as a positive control. Note the presence of FGF21 in both cell types.